R&D notes from agent experiments

Short findings from model selection, retrieval behavior, tool calling, evaluation, and failure-case testing.

Why this note exists.

R&D is useful when it reduces delivery uncertainty. Experiments should help the team decide what is reliable enough to use and what must stay behind a human review boundary.

Apply this pattern

Bring the messy context. Leave with a clearer path.

Share the current workflow, tools, examples, and risks. Levinci will route it toward the right service path.